Title :
Pulse stream current mode CMOS CNN chip
Author :
Paasio, An ; Dawidziuk, Adam ; Porra, Veikko
Author_Institution :
Electron. Circuit Design Lab., Helsinki Univ. of Technol., Espoo, Finland
Abstract :
A new idea of analog cellular neural network (CNN) VLSI implementation is described. The main problem in neural networks realization is the size of adjustable connections between neurons in the net. The weight circuits may occupy more than 90% of the single neuron space. The main advantage of current mode pulse stream neurons is small size of the weight circuit. The simplicity of the building blocks used allows one to operate them with relatively high speed. As compared with the other pulse stream circuits, this approach is based on current pulses. Therefore, for both basic neural operations, summation and multiplication are easy to implement, if only the phase is irrelevant
Keywords :
CMOS analogue integrated circuits; VLSI; analogue processing circuits; cellular neural nets; neural chips; CMOS neural chip; VLSI; analog cellular neural network; current pulses; pulse stream current mode; weight circuits; CMOS technology; Cellular neural networks; Frequency; Neurons; Pulse circuits; Pulse generation; Space vector pulse width modulation; Switches; Very large scale integration; Voltage;
Conference_Titel :
Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
Conference_Location :
Seville
Print_ISBN :
0-7803-3261-X
DOI :
10.1109/CNNA.1996.566617